For configurations that have the kconfig option NUMA_KEEP_MEMINFO
disabled numa_fill_memblks() only returns with NUMA_NO_MEMBLK (-1).
SRAT lookup fails then because an existing SRAT memory range cannot be
found for a CFMWS address range. This causes the addition of a
duplicate numa_memblk with a different node id and a subsequent page
fault and kernel crash during boot.
Fix this by making numa_fill_memblks() always available regardless of
NUMA_KEEP_MEMINFO.
The fix also removes numa_fill_memblks() from sparsemem.h using
__weak.
>From Dan:
"""
It just feels like numa_fill_memblks() has absolutely no business being
defined in arch/x86/include/asm/sparsemem.h.
The only use for numa_fill_memblks() is to arrange for NUMA nodes to be
applied to memory ranges hot-onlined by the CXL driver.
It belongs right next to numa_add_memblk(), and I suspect
arch/x86/include/asm/sparsemem.h was only chosen to avoid figuring out
what to do about the fact that linux/numa.h does not include asm/numa.h
and that all implementations either provide numa_add_memblk() or select
the generic implementation.
So I would prefer that this do the proper fix and get
numa_fill_memblks() completely out of the sparsemem.h path.
Something like the following which boots for me.
"""
Note that the issue was initially introduced with [1]. But since
phys_to_target_node() was originally used that returned the valid node
0, an additional numa_memblk was not added. Though, the node id was
wrong too, a message is seen then in the logs:
kernel/numa.c: pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
[1] commit fd49f99c1809 ("ACPI: NUMA: Add a node and memblk for each
CFMWS not in SRAT")
Suggested-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Link: https://lore.kernel.org/all/66271b0072317_69102944c@xxxxxxxxxxxxxxxxxxxxxxxxx.notmuch/
Fixes: 8f1004679987 ("ACPI/NUMA: Apply SRAT proximity domain to entire CFMWS window")
Cc: Derick Marks <derick.w.marks@xxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Alison Schofield <alison.schofield@xxxxxxxxx>
Signed-off-by: Robert Richter <rrichter@xxxxxxx>
---
Authorship can be changed to Dan's if he wants to but that needs his
Signed-off-by.
---
arch/x86/include/asm/numa.h | 1 +
arch/x86/include/asm/sparsemem.h | 2 --
arch/x86/mm/numa.c | 4 ++--
drivers/acpi/numa/srat.c | 5 +++++
include/linux/numa.h | 7 -------
5 files changed, 8 insertions(+), 11 deletions(-)
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index ef2844d69173..12a93a3466c4 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -26,6 +26,7 @@ extern s16 __apicid_to_node[MAX_LOCAL_APIC];
extern nodemask_t numa_nodes_parsed __initdata;
extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+extern int __init numa_fill_memblks(u64 start, u64 end);
extern void __init numa_set_distance(int from, int to, int distance);
static inline void set_apicid_to_node(int apicid, s16 node)
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 1be13b2dfe8b..64df897c0ee3 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -37,8 +37,6 @@ extern int phys_to_target_node(phys_addr_t start);
#define phys_to_target_node phys_to_target_node
extern int memory_add_physaddr_to_nid(u64 start);
#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
-extern int numa_fill_memblks(u64 start, u64 end);
-#define numa_fill_memblks numa_fill_memblks
#endif
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 65e9a6e391c0..ce84ba86e69e 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -929,6 +929,8 @@ int memory_add_physaddr_to_nid(u64 start)
}
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+#endif
+
static int __init cmp_memblk(const void *a, const void *b)
{
const struct numa_memblk *ma = *(const struct numa_memblk **)a;
@@ -1001,5 +1003,3 @@ int __init numa_fill_memblks(u64 start, u64 end)
}
return 0;
}
-
-#endif
diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index e45e64993c50..3b09fd39eeb4 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -208,6 +208,11 @@ int __init srat_disabled(void)
return acpi_numa < 0;
}
+__weak int __init numa_fill_memblks(u64 start, u64 end)
+{
+ return NUMA_NO_MEMBLK;
+}
+
#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH)
/*
* Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for
diff --git a/include/linux/numa.h b/include/linux/numa.h
index 915033a75731..8485d98e554d 100644
--- a/include/linux/numa.h
+++ b/include/linux/numa.h
@@ -36,13 +36,6 @@ int memory_add_physaddr_to_nid(u64 start);
int phys_to_target_node(u64 start);
#endif
-#ifndef numa_fill_memblks
-static inline int __init numa_fill_memblks(u64 start, u64 end)
-{
- return NUMA_NO_MEMBLK;
-}
-#endif
-
#else /* !CONFIG_NUMA */
static inline int numa_nearest_node(int node, unsigned int state)
{
--
2.39.2
